{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LPPMRDU7FMRRZ2YLTZ3EZWARNK","short_pith_number":"pith:LPPMRDU7","schema_version":"1.0","canonical_sha256":"5bdec88e9f2b231ceb0b9e764cd8116a8577006b87c6ff6306434b73b231482a","source":{"kind":"arxiv","id":"2006.10524","version":3},"attestation_state":"computed","paper":{"title":"Reinforcement Learning as Iterative and Amortised Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Tschantz, Anil K Seth, Beren Millidge, Christopher L Buckley","submitted_at":"2020-06-13T16:10:03Z","abstract_excerpt":"There are several ways to categorise reinforcement learning (RL) algorithms, such as either model-based or model-free, policy-based or planning-based, on-policy or off-policy, and online or offline. Broad classification schemes such as these help provide a unified perspective on disparate techniques and can contextualise and guide the development of new algorithms. In this paper, we utilise the control as inference framework to outline a novel classification scheme based on amortised and iterative inference. We demonstrate that a wide range of algorithms can be classified in this manner provid"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2006.10524","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-13T16:10:03Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"df2f462447a6d6350e71aaae8be5ade9328089a80b1993024c194c884cbcee77","abstract_canon_sha256":"eb44181722d6a2cfcefb94bcb01f5f86b30eab13d91f2bb598daa404d3e73009"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:16:15.998224Z","signature_b64":"CZB+9cdUOso///CrpW5On/X7IBazP2wJSJUxsPIQeZpLpccOFk2/0oXKgNE8gCVq2WM0GsDKJ6y+71rPvEoYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bdec88e9f2b231ceb0b9e764cd8116a8577006b87c6ff6306434b73b231482a","last_reissued_at":"2026-07-05T01:16:15.997863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:16:15.997863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning as Iterative and Amortised Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Tschantz, Anil K Seth, Beren Millidge, Christopher L Buckley","submitted_at":"2020-06-13T16:10:03Z","abstract_excerpt":"There are several ways to categorise reinforcement learning (RL) algorithms, such as either model-based or model-free, policy-based or planning-based, on-policy or off-policy, and online or offline. Broad classification schemes such as these help provide a unified perspective on disparate techniques and can contextualise and guide the development of new algorithms. In this paper, we utilise the control as inference framework to outline a novel classification scheme based on amortised and iterative inference. We demonstrate that a wide range of algorithms can be classified in this manner provid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10524","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.10524/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2006.10524","created_at":"2026-07-05T01:16:15.997916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.10524v3","created_at":"2026-07-05T01:16:15.997916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10524","created_at":"2026-07-05T01:16:15.997916+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPPMRDU7FMRR","created_at":"2026-07-05T01:16:15.997916+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPPMRDU7FMRRZ2YL","created_at":"2026-07-05T01:16:15.997916+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPPMRDU7","created_at":"2026-07-05T01:16:15.997916+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LPPMRDU7FMRRZ2YLTZ3EZWARNK","json":"https://pith.science/pith/LPPMRDU7FMRRZ2YLTZ3EZWARNK.json","graph_json":"https://pith.science/api/pith-number/LPPMRDU7FMRRZ2YLTZ3EZWARNK/graph.json","events_json":"https://pith.science/api/pith-number/LPPMRDU7FMRRZ2YLTZ3EZWARNK/events.json","paper":"https://pith.science/paper/LPPMRDU7"},"agent_actions":{"view_html":"https://pith.science/pith/LPPMRDU7FMRRZ2YLTZ3EZWARNK","download_json":"https://pith.science/pith/LPPMRDU7FMRRZ2YLTZ3EZWARNK.json","view_paper":"https://pith.science/paper/LPPMRDU7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.10524&json=true","fetch_graph":"https://pith.science/api/pith-number/LPPMRDU7FMRRZ2YLTZ3EZWARNK/graph.json","fetch_events":"https://pith.science/api/pith-number/LPPMRDU7FMRRZ2YLTZ3EZWARNK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPPMRDU7FMRRZ2YLTZ3EZWARNK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPPMRDU7FMRRZ2YLTZ3EZWARNK/action/storage_attestation","attest_author":"https://pith.science/pith/LPPMRDU7FMRRZ2YLTZ3EZWARNK/action/author_attestation","sign_citation":"https://pith.science/pith/LPPMRDU7FMRRZ2YLTZ3EZWARNK/action/citation_signature","submit_replication":"https://pith.science/pith/LPPMRDU7FMRRZ2YLTZ3EZWARNK/action/replication_record"}},"created_at":"2026-07-05T01:16:15.997916+00:00","updated_at":"2026-07-05T01:16:15.997916+00:00"}